[myspass] Move into own file and default to mp4 ext

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 4002c9485d394b75d89be4f5a444d9f40c421a4d..c3d0e619130c05dc7cc863ec45f2f184c8c03fa7 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -35,9 +35,11 @@ from .extractor.googleplus import GooglePlusIE
 from .extractor.googlesearch import GoogleSearchIE
 from .extractor.infoq import InfoQIE
 from .extractor.justintv import JustinTVIE
+from .extractor.keek import KeekIE
 from .extractor.metacafe import MetacafeIE
 from .extractor.mixcloud import MixcloudIE
 from .extractor.mtv import MTVIE
+from .extractor.myspass import MySpassIE
 from .extractor.myvideo import MyVideoIE
 from .extractor.nba import NBAIE
 from .extractor.statigram import StatigramIE
@@ -85,88 +87,8 @@ from .extractor.zdf import ZDFIE
 
 
 
-class KeekIE(InfoExtractor):
-    _VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
-    IE_NAME = u'keek'
-
-    def _real_extract(self, url):
-        m = re.match(self._VALID_URL, url)
-        video_id = m.group('videoID')
-
-        video_url = u'http://cdn.keek.com/keek/video/%s' % video_id
-        thumbnail = u'http://cdn.keek.com/keek/thumbnail/%s/w100/h75' % video_id
-        webpage = self._download_webpage(url, video_id)
-
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(?P<title>.*?)"',
-            webpage, u'title')
-
-        uploader = self._html_search_regex(r'<div class="user-name-and-bio">[\S\s]+?<h2>(?P<uploader>.+?)</h2>',
-            webpage, u'uploader', fatal=False)
-
-        info = {
-                'id': video_id,
-                'url': video_url,
-                'ext': 'mp4',
-                'title': video_title,
-                'thumbnail': thumbnail,
-                'uploader': uploader
-        }
-        return [info]
 
 
-class MySpassIE(InfoExtractor):
-    _VALID_URL = r'http://www.myspass.de/.*'
-
-    def _real_extract(self, url):
-        META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
-
-        # video id is the last path element of the URL
-        # usually there is a trailing slash, so also try the second but last
-        url_path = compat_urllib_parse_urlparse(url).path
-        url_parent_path, video_id = os.path.split(url_path)
-        if not video_id:
-            _, video_id = os.path.split(url_parent_path)
-
-        # get metadata
-        metadata_url = META_DATA_URL_TEMPLATE % video_id
-        metadata_text = self._download_webpage(metadata_url, video_id)
-        metadata = xml.etree.ElementTree.fromstring(metadata_text.encode('utf-8'))
-
-        # extract values from metadata
-        url_flv_el = metadata.find('url_flv')
-        if url_flv_el is None:
-            raise ExtractorError(u'Unable to extract download url')
-        video_url = url_flv_el.text
-        extension = os.path.splitext(video_url)[1][1:]
-        title_el = metadata.find('title')
-        if title_el is None:
-            raise ExtractorError(u'Unable to extract title')
-        title = title_el.text
-        format_id_el = metadata.find('format_id')
-        if format_id_el is None:
-            format = ext
-        else:
-            format = format_id_el.text
-        description_el = metadata.find('description')
-        if description_el is not None:
-            description = description_el.text
-        else:
-            description = None
-        imagePreview_el = metadata.find('imagePreview')
-        if imagePreview_el is not None:
-            thumbnail = imagePreview_el.text
-        else:
-            thumbnail = None
-        info = {
-            'id': video_id,
-            'url': video_url,
-            'title': title,
-            'ext': extension,
-            'format': format,
-            'thumbnail': thumbnail,
-            'description': description
-        }
-        return [info]
 
 class SpiegelIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'